SergejSchweizer's picture
First training of SnowballTarget
2e8ce14
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9751015305519104,
"min": 0.9751015305519104,
"max": 2.859116315841675,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9310.26953125,
"min": 9310.26953125,
"max": 29280.2109375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.541969299316406,
"min": 0.5209303498268127,
"max": 12.541969299316406,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2445.68408203125,
"min": 101.06048583984375,
"max": 2508.48486328125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0667705280837111,
"min": 0.06381662999183926,
"max": 0.07607813345670116,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2670821123348444,
"min": 0.2619092455186582,
"max": 0.3803906672835058,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22493930650400182,
"min": 0.14441304234331293,
"max": 0.29525191066604034,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8997572260160073,
"min": 0.5776521693732517,
"max": 1.3641164025255277,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.954545454545453,
"min": 3.977272727272727,
"max": 24.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 175.0,
"max": 1361.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.977272727272727,
"max": 24.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 175.0,
"max": 1361.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1673641877",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673642390"
},
"total": 513.1551252090001,
"count": 1,
"self": 0.4949930050001967,
"children": {
"run_training.setup": {
"total": 0.12980883399995946,
"count": 1,
"self": 0.12980883399995946
},
"TrainerController.start_learning": {
"total": 512.5303233699999,
"count": 1,
"self": 0.6515385500013053,
"children": {
"TrainerController._reset_env": {
"total": 11.149777384000117,
"count": 1,
"self": 11.149777384000117
},
"TrainerController.advance": {
"total": 500.57696556299857,
"count": 18201,
"self": 0.34499893898373557,
"children": {
"env_step": {
"total": 500.23196662401483,
"count": 18201,
"self": 330.5071368580004,
"children": {
"SubprocessEnvManager._take_step": {
"total": 169.38715582999566,
"count": 18201,
"self": 1.6956862679896858,
"children": {
"TorchPolicy.evaluate": {
"total": 167.69146956200598,
"count": 18201,
"self": 38.53506915402909,
"children": {
"TorchPolicy.sample_actions": {
"total": 129.1564004079769,
"count": 18201,
"self": 129.1564004079769
}
}
}
}
},
"workers": {
"total": 0.33767393601874574,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 510.91928755698837,
"count": 18201,
"is_parallel": true,
"self": 240.96006132897742,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008640796999998201,
"count": 1,
"is_parallel": true,
"self": 0.003927801999907388,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004712995000090814,
"count": 10,
"is_parallel": true,
"self": 0.004712995000090814
}
}
},
"UnityEnvironment.step": {
"total": 0.05243964999999662,
"count": 1,
"is_parallel": true,
"self": 0.0004188519999388518,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003187869999692339,
"count": 1,
"is_parallel": true,
"self": 0.0003187869999692339
},
"communicator.exchange": {
"total": 0.04949073800003134,
"count": 1,
"is_parallel": true,
"self": 0.04949073800003134
},
"steps_from_proto": {
"total": 0.00221127300005719,
"count": 1,
"is_parallel": true,
"self": 0.0005115919998388563,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016996810002183338,
"count": 10,
"is_parallel": true,
"self": 0.0016996810002183338
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 269.95922622801095,
"count": 18200,
"is_parallel": true,
"self": 10.258632653977884,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.857953958014832,
"count": 18200,
"is_parallel": true,
"self": 5.857953958014832
},
"communicator.exchange": {
"total": 214.00349195301624,
"count": 18200,
"is_parallel": true,
"self": 214.00349195301624
},
"steps_from_proto": {
"total": 39.839147663001995,
"count": 18200,
"is_parallel": true,
"self": 8.431874014029745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.40727364897225,
"count": 182000,
"is_parallel": true,
"self": 31.40727364897225
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.031199998484226e-05,
"count": 1,
"self": 5.031199998484226e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 496.68494697187066,
"count": 429230,
"is_parallel": true,
"self": 11.738065006958095,
"children": {
"process_trajectory": {
"total": 284.6162140749143,
"count": 429230,
"is_parallel": true,
"self": 283.8167670109142,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7994470640001055,
"count": 4,
"is_parallel": true,
"self": 0.7994470640001055
}
}
},
"_update_policy": {
"total": 200.33066788999827,
"count": 90,
"is_parallel": true,
"self": 53.9536228990014,
"children": {
"TorchPPOOptimizer.update": {
"total": 146.37704499099686,
"count": 4587,
"is_parallel": true,
"self": 146.37704499099686
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1519915609999316,
"count": 1,
"self": 0.0009623919997920893,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15102916900013952,
"count": 1,
"self": 0.15102916900013952
}
}
}
}
}
}
}